Daily Papers of 2024-06-27

  1. Adam-mini: Use Fewer Learning Rates To Gain More 60 upvotes, #1 of 2024-06-27
  2. Octo-planner: On-device Language Model for Planner-Action Agents 45 upvotes, #2 of 2024-06-27
  3. ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation 37 upvotes, #3 of 2024-06-27
  4. CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs 25 upvotes, #4 of 2024-06-27
  5. A Closer Look into Mixture-of-Experts in Large Language Models 12 upvotes, #5 of 2024-06-27
  6. EHRCon: Dataset for Checking Consistency between Unstructured Notes and Structured Tables in Electronic Health Records 11 upvotes, #6 of 2024-06-27
  7. WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs 11 upvotes, #6 of 2024-06-27
  8. MatchTime: Towards Automatic Soccer Game Commentary Generation 11 upvotes, #6 of 2024-06-27
  9. Symbolic Learning Enables Self-Evolving Agents 9 upvotes, #9 of 2024-06-27
  10. Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning 8 upvotes, #10 of 2024-06-27
  11. Understanding and Diagnosing Deep Reinforcement Learning 8 upvotes, #10 of 2024-06-27
  12. Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models 8 upvotes, #10 of 2024-06-27
  13. WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models 7 upvotes, #13 of 2024-06-27
  14. MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Pool 5 upvotes, #14 of 2024-06-27

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.